##// END OF EJS Templates
deltas: set estimated compression upper bound to "3x" instead of "10x"...
deltas: set estimated compression upper bound to "3x" instead of "10x" In pratice, we very rarely observer compression better than "3x" on manifest deltas. Having a more aggressive estimate significantly helps our pathological use case on a private repository. Here are a comparison of timings using different upper bound. Estimated compression | ø | ×10 | ×5 | ×3 | timing | 14.11 | 2.61 | 1.96 | 1.53 | We also tested the impact of this series on an array of public repositories. This shown no impact in either size nor timing. Full data set below for those interested. Size ---- Regarding size, not significant impact have been noticed on neither public nor private repositories. Here are the number we gathered on public repositories: zlib/upperbound | no | 10x | 5x | 3x mercurial | 5 875 730 | 5 875 730 | 5 875 730 | 5 875 730 pypy | 27 782 913 | 27 782 913 | 27 782 913 | 27 782 913 netbeans | 159 161 207 | 159 161 207 | 159 161 207 | 159 959 879 (+0.5%) mozilla-central | 323 841 642 | 323 841 642 | 323 841 642 | 319 867 519 (-2.5%) mozilla-try | 746 649 123 | 746 649 123 | 746 649 123 | 741 155 568 (-0.7%) private-repo | 1 485 287 294 | 1 485 287 294 | 1 485 287 294 | 1 409 248 382 (-5.1%) zstd/upperbound | no | 10x | 5x | 3x mercurial | 5 895 206 | 5 895 206 | 5 895 206 | 5 895 206 pypy | 28 689 230 | 28 689 230 | 28 689 230 | 28 689 230 netbeans | 157 636 387 | 157 636 387 | 157 636 387 | 159 692 678 (+1.3%) mozilla-central | 317 650 281 | 317 650 281 | 317 650 281 | 319 613 603 (+0.6%) mozilla-try | 737 555 275 | 737 555 275 | 737 555 275 | 738 079 473 (+0.1%) private-repo | 1 352 362 982 | 1 352 362 982 | 1 346 961 880 | 1 361 327 384 (+0.7%) Speed ------ Timing gathered using `hg perfrevlogwrite -m`. Value are in seconds. mercurial zlib | no | 10x | 5x | 3x | total | 65.551783 | 65.388887 | 65.260658 | 65.321199 | max | 0.034544 | 0.034571 | 0.034659 | 0.034521 | 99.99% | 0.034544 | 0.034571 | 0.034659 | 0.034521 | zstd | no | 10x | 5x | 3x | total | 49.118449 | 49.054062 | 48.753588 | 48.740230 | max | 0.009338 | 0.009239 | 0.009202 | 0.009178 | 99.99% | 0.007618 | 0.007639 | 0.007626 | 0.007621 | pypy zlib | no | 10x | 5x | 3x | total | 560.865984 | 558.983817 | 559.083815 | 559.349152 | max | 0.219614 | 0.215922 | 0.218112 | 0.218107 | 99.99% | 0.219614 | 0.215922 | 0.218112 | 0.218107 | zstd | no | 10x | 5x | 3x | total | 349.393280 | 347.395819 | 347.185407 | 345.643985 | max | 0.084143 | 0.083536 | 0.081834 | 0.082178 | 99.99% | 0.039445 | 0.039639 | 0.039612 | 0.039175 | netbeans zlib | no | 10x | 5x | 3x | total | 33103.327727 | 33314.932260 | 33211.745233 | 33345.891778 | max | 2.666852 | 2.672059 | 2.662453 | 2.662936 | 99.99% | 2.058772 | 2.070429 | 2.069569 | 2.064653 | zstd | no | 10x | 5x | 3x | total | 20112.102708 | 20095.879719 | 20083.390300 | 20123.221859 | max | 2.063482 | 2.062851 | 2.065229 | 2.060147 | 99.99% | 1.146647 | 1.143794 | 1.142933 | 1.146529 | mozilla zlib | no | 10x | 5x | 3x | total | 41374.102138 | 41418.816773 | 41381.956370 | 41334.280732 | max | 3.383474 | 3.387400 | 3.405711 | 3.387316 | 99.99% | 1.006755 | 1.005954 | 1.007700 | 1.007373 | zstd | no | 10x | 5x | 3x | total | 24689.691520 | 24643.939662 | 24664.630027 | 24664.512714 | max | 1.460822 | 1.449640 | 1.439747 | 1.465304 | 99.99% | 0.527111 | 0.527377 | 0.527807 | 0.527226 |

File last commit:

r40195:5774fc62 default
r42669:4a3abb33 default
Show More
urllibcompat.py
196 lines | 5.3 KiB | text/x-python | PythonLexer
Augie Fackler
urllibcompat: new library to help abstract out some python3 urllib2 stuff...
r34466 # urllibcompat.py - adapters to ease using urllib2 on Py2 and urllib on Py3
#
# Copyright 2017 Google, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
from . import pycompat
Augie Fackler
urllibcompat: move some adapters from pycompat to urllibcompat...
r34468 _sysstr = pycompat.sysstr
class _pycompatstub(object):
def __init__(self):
self._aliases = {}
def _registeraliases(self, origin, items):
"""Add items that will be populated at the first access"""
items = map(_sysstr, items)
self._aliases.update(
Yuya Nishihara
py3: use r'' instead of sysstr('') to get around code transformer...
r36853 (item.replace(r'_', r'').lower(), (origin, item))
Augie Fackler
urllibcompat: move some adapters from pycompat to urllibcompat...
r34468 for item in items)
def _registeralias(self, origin, attr, name):
"""Alias ``origin``.``attr`` as ``name``"""
self._aliases[_sysstr(name)] = (origin, _sysstr(attr))
def __getattr__(self, name):
try:
origin, item = self._aliases[name]
except KeyError:
raise AttributeError(name)
self.__dict__[name] = obj = getattr(origin, item)
return obj
httpserver = _pycompatstub()
urlreq = _pycompatstub()
urlerr = _pycompatstub()
Augie Fackler
urllibcompat: new library to help abstract out some python3 urllib2 stuff...
r34466 if pycompat.ispy3:
Augie Fackler
urllibcompat: move some adapters from pycompat to urllibcompat...
r34468 import urllib.parse
urlreq._registeraliases(urllib.parse, (
"splitattr",
"splitpasswd",
"splitport",
"splituser",
"urlparse",
"urlunparse",
))
Gregory Szorc
wireprotoserver: define and use parse_qs from urllib...
r36094 urlreq._registeralias(urllib.parse, "parse_qs", "parseqs")
Gregory Szorc
hgweb: teach WSGI parser about query strings...
r36827 urlreq._registeralias(urllib.parse, "parse_qsl", "parseqsl")
Augie Fackler
urllibcompat: move some adapters from pycompat to urllibcompat...
r34468 urlreq._registeralias(urllib.parse, "unquote_to_bytes", "unquote")
import urllib.request
urlreq._registeraliases(urllib.request, (
"AbstractHTTPHandler",
"BaseHandler",
"build_opener",
"FileHandler",
"FTPHandler",
"ftpwrapper",
"HTTPHandler",
"HTTPSHandler",
"install_opener",
"pathname2url",
"HTTPBasicAuthHandler",
"HTTPDigestAuthHandler",
"HTTPPasswordMgrWithDefaultRealm",
"ProxyHandler",
"Request",
"url2pathname",
"urlopen",
))
import urllib.response
urlreq._registeraliases(urllib.response, (
"addclosehook",
"addinfourl",
))
import urllib.error
urlerr._registeraliases(urllib.error, (
"HTTPError",
"URLError",
))
import http.server
httpserver._registeraliases(http.server, (
"HTTPServer",
"BaseHTTPRequestHandler",
"SimpleHTTPRequestHandler",
"CGIHTTPRequestHandler",
))
# urllib.parse.quote() accepts both str and bytes, decodes bytes
# (if necessary), and returns str. This is wonky. We provide a custom
# implementation that only accepts bytes and emits bytes.
def quote(s, safe=r'/'):
Gregory Szorc
py3: coerce bytestr to bytes to appease urllib.parse.quote_from_bytes()...
r40195 # bytestr has an __iter__ that emits characters. quote_from_bytes()
# does an iteration and expects ints. We coerce to bytes to appease it.
if isinstance(s, pycompat.bytestr):
s = bytes(s)
Augie Fackler
urllibcompat: move some adapters from pycompat to urllibcompat...
r34468 s = urllib.parse.quote_from_bytes(s, safe=safe)
return s.encode('ascii', 'strict')
# urllib.parse.urlencode() returns str. We use this function to make
# sure we return bytes.
def urlencode(query, doseq=False):
s = urllib.parse.urlencode(query, doseq=doseq)
return s.encode('ascii')
urlreq.quote = quote
urlreq.urlencode = urlencode
Augie Fackler
urllibcompat: new library to help abstract out some python3 urllib2 stuff...
r34466
def getfullurl(req):
return req.full_url
def gethost(req):
return req.host
def getselector(req):
return req.selector
def getdata(req):
return req.data
def hasdata(req):
return req.data is not None
else:
Augie Fackler
urllibcompat: move some adapters from pycompat to urllibcompat...
r34468 import BaseHTTPServer
import CGIHTTPServer
import SimpleHTTPServer
import urllib2
import urllib
import urlparse
urlreq._registeraliases(urllib, (
"addclosehook",
"addinfourl",
"ftpwrapper",
"pathname2url",
"quote",
"splitattr",
"splitpasswd",
"splitport",
"splituser",
"unquote",
"url2pathname",
"urlencode",
))
urlreq._registeraliases(urllib2, (
"AbstractHTTPHandler",
"BaseHandler",
"build_opener",
"FileHandler",
"FTPHandler",
"HTTPBasicAuthHandler",
"HTTPDigestAuthHandler",
"HTTPHandler",
"HTTPPasswordMgrWithDefaultRealm",
"HTTPSHandler",
"install_opener",
"ProxyHandler",
"Request",
"urlopen",
))
urlreq._registeraliases(urlparse, (
"urlparse",
"urlunparse",
))
Gregory Szorc
wireprotoserver: define and use parse_qs from urllib...
r36094 urlreq._registeralias(urlparse, "parse_qs", "parseqs")
Gregory Szorc
hgweb: teach WSGI parser about query strings...
r36827 urlreq._registeralias(urlparse, "parse_qsl", "parseqsl")
Augie Fackler
urllibcompat: move some adapters from pycompat to urllibcompat...
r34468 urlerr._registeraliases(urllib2, (
"HTTPError",
"URLError",
))
httpserver._registeraliases(BaseHTTPServer, (
"HTTPServer",
"BaseHTTPRequestHandler",
))
httpserver._registeraliases(SimpleHTTPServer, (
"SimpleHTTPRequestHandler",
))
httpserver._registeraliases(CGIHTTPServer, (
"CGIHTTPRequestHandler",
))
Augie Fackler
urllibcompat: new library to help abstract out some python3 urllib2 stuff...
r34466
def gethost(req):
return req.get_host()
def getselector(req):
return req.get_selector()
def getfullurl(req):
return req.get_full_url()
def getdata(req):
return req.get_data()
def hasdata(req):
return req.has_data()